Update app.py

app.py

@@ -0,0 +1,49 @@
+from sklearn.feature_extraction.text import TfidfVectorizer
+from TurkishStemmer import TurkishStemmer
+import nltk
+import string
+# import for loading python objects (scikit-learn models)
+import pickle
+
+def custom_tokenizer_with_Turkish_stemmer(text):
+    # my text was unicode so I had to use the unicode-specific translate function. If your documents are strings, you will need to use a different `translate` function here. `Translated` here just does search-replace. See the trans_table: any matching character in the set is replaced with `None`
+    tokens = [word for word in nltk.word_tokenize(text.translate(trans_table))]
+    stems = [stemmerTR.stem(item.lower()) for item in tokens]
+    return stems
+
+def predictSMSdata(test_text):
+    categories = ["legitimate", "spam"]
+    categories.sort()
+
+    # load model
+    filename1 = "LinearSVC_SMS_spam_TR.pickle"
+    file_handle1 = open(filename1, "rb")
+    classifier = pickle.load(file_handle1)
+    file_handle1.close()
+
+    # load tfidf_vectorizer for transforming test text data
+    filename2 = "tfidf_vectorizer_TR.pickle"
+    file_handle2 = open(filename2, "rb")
+    tfidf_vectorizer = pickle.load(file_handle2)
+    file_handle2.close()
+
+    test_list=[test_text]
+    tfidf_vectorizer_vectors_test = tfidf_vectorizer.transform(test_list)
+    predicted = classifier.predict(tfidf_vectorizer_vectors_test)
+    print(categories[predicted[0]])
+
+trans_table = {ord(c): None for c in string.punctuation + string.digits}
+stemmerTR = TurkishStemmer()
+
+# Extra test data from the training set
+# legitimate - l0430.txt
+predictSMSdata("Ahmet de gelecek mi?")
+
+# legitimate - l0429.txt
+predictSMSdata("Vakifbank WebSubem girisi icin tek kullanimlik sifreniz: 160038 . Sifreniz 3 dk gecerlidir. Tarih: 14.02.2011 Saat: 13:53")
+
+# spam - s0003.txt
+predictSMSdata("Aveadan SUPER bir Muzik Paketi! MAXI yaz, 5555e gonder, Maxi Muzikindir Paketi ile 150 yerli 50 Yabanci sarkiyi ayda sadece 5,99 TLye cebine indir!")
+
+# spam - s0359.txt
+predictSMSdata("1-2 NISAN TARIHLERINDE;DERMALOGICA CILT BAKIMINA DAVETLISINIZ.RANDEVU ALINIZ TEL:2312840")